Wayfair Tech Blog

Lynx: Identifying Wayfair Customers’ Functional Needs

Introduction

Wayfair DS Explains It All: Jinnie Chen on Product Tagging

Product tags reveals the detailed characteristics of a product which can be used to power PDP (product display page) creation, searching, filter creation and more.This week in Wayfair Data Science’s explainer series, Senior Data Scientist Jinnie Chen outlines some of the strategies we applied in Wayfair to perform automated product tagging.

Wayfair Tech Blog

Getting The Most Out of XML and Exploring Anko Layouts for Android

Domain-specific languages (DSLs) – are they worth the hype? In a recent investigation, our Berlin-based Android Team were looking to further optimize Wayfair’s Android app, and were looking around for options. With the inconvenience of creating a UI in XML, and the appeal of a language that focuses on a specific aspect of an application, our team chose to give Anko Layouts a try.

Wayfair Tech Blog

Wayfair DS Explains It All: Cole Zuber on Evaluating Recommender Systems

Serving effective personalized product recommendations is critical to providing a pleasant shopping experience for customers at Wayfair. To do this, the Wayfair Data Science team builds state of the art recommender systems that leverage the customer’s previous browsing history to surface products that match their interests. This week in Wayfair Data Science’s explainer series, Senior Data Scientist Cole Zuber describes how we approach evaluating these recommender systems.

Wayfair Tech Blog

Wayfair DS Explains It All: Trent Woodbury on Handling Imbalanced Data

Most machine learning algorithms are designed to train on balanced datasets. Resultantly, when our data are highly imbalanced, a typical model will have atrocious recall. In this video, Wayfair Senior Data Scientist Trent Woodbury explains the three most common ways of handling this imbalanced data problem.

Wayfair Tech Blog

Meet Jen Wang: Chemist. Traditional Chinese Medicine Enthusiast. Data Scientist.

How does a chemist with a postdoc in drug design end up working as a data scientist at an e-commerce home furnishings company? “Ha, so it’s a long story actually,” says Jen Wang, data science manager on the Marketing team at Wayfair.

Wayfair Tech Blog

Meet John Walk: Ice Climber. Nuclear Physicist. Data Scientist.

John stands out in a room. With a flaming red beard and an arm of tattoos, he looks like he might be more at home in a Nordic tavern than an office. But once you notice his Captain Hammer t-shirt, the Gandalf action figure on his desk, and start talking to him about Nuclear Physics, you see that he’s right at home in a room full of data scientists.

Wayfair Tech Blog

Wayfair DS Explains It All: Peter B. Golbus on Theoretical Machine Learning

This week in Wayfair Data Science’s Explainer Series, Data Science Tech Lead Peter B. Golbus discusses machine learning from a theoretical computer science perspective. In this video, we describe multiclass classification as an encoding task, i.e. a process for building compression schemes that convert large "files" (feature vectors) into small ones (labels). By framing classification this way, we are able to use the powerful tools of Information Theory to produce actionable insight. In particular, we discuss that classification accuracy is bounded from above by the mutual information between your features and labels, and how information theory explains why ensembling and feature selection are such powerful tools for machine learning.

Wayfair Tech Blog

Open Tracing for iOS: A Performance Tool for Everyone

The App Platforms Team at Wayfair, empowering a team of more than 60 mobile developers with efficient tooling and processes, has been actively looking at the performance of it’s mobile offerings, turning this into more focused work in the past few months. We wanted to involve as many of the brilliant minds working at Wayfair as possible to understand the question around performance, and to find concrete solutions.